© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85579
    Prev
    Next
    INDEX
    Explanations

    fizz buzz, zipper pockets, Jeremiah Johnson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    辚
    -3.50
    筴
    -2.80
    秝
    -2.69
     tématu
    -2.69
    咈
    -2.64
    甡
    -2.64
    酩
    -2.63
    餿
    -2.58
     become
    -2.56
    で行
    -2.55
    POSITIVE LOGITS
    s
    3.84
    的
    3.02
    h
    2.66
    是個
    2.48
    when
    2.44
     défis
    2.38
    ’
    2.31
    麪
    2.20
    .
    2.20
    贾
    2.16
    Activations Density 0.007%

    No Known Activations